© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129542
    Prev
    Next
    INDEX
    Explanations

    programming language file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     there
    -0.08
    ・
    -0.06
     a
    -0.06
     it
    -0.06
    .
    -0.06
     परफॉर्म
    -0.06
    ,
    -0.06
     Er
    -0.06
     we
    -0.06
     of
    -0.06
    POSITIVE LOGITS
    Because
    0.07
     heutigen
    0.07
    Until
    0.06
     உன்
    0.06
    あなたの
    0.06
     heut
    0.06
     बृहस्पतिवार
    0.06
    和其他
    0.06
     চিৎকার
    0.06
    ujen
    0.06
    Activations Density 0.011%

    No Known Activations